#4545th of 81 in VoiceFor voice, speech and music
neuralnote
Audio plugin that transcribes audio to multi-instrument MIDI locally in a DAW
- Stars
- 3.5k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- C++
2,544 on 20 Apr 20263,456 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
NeuralNote is a VST3/AU/Standalone plugin that transcribes audio to MIDI inside a DAW using MuScriptor models (small, medium, large) run through a C++/ggml engine. It handles full mixes with notes grouped per instrument, includes a built-in synth for playback, and runs on GPU (Metal, Vulkan) or CPU. Audio stays on the machine; the app goes online only to download models and check for updates.
Who it is for: Musicians and producers who want local audio-to-MIDI transcription in their DAW
Strengths
- Multi-instrument transcription of full mixes, with per-instrument gain, mute and solo in a built-in synth
- Runs locally on Metal, Vulkan or CPU; audio never leaves the machine
- Transcription can be paused and resumed, even after reopening the DAW session
- Engine is a separate MIT-licensed C++/ggml library (muscriptor.cpp) that can be reused
Weaknesses
- MuScriptor weights are CC BY-NC 4.0, so non-commercial use only
- Large model runs about 0.5x real time on an M1 Pro GPU; CPU not recommended
- No prebuilt Linux binaries yet; only Clang builds have been tested
- Windows installer is not code signed, and only a few GPUs are tested
What it needs
- GPU optional
- Needs Hugging Face (model download), Vulkan SDK (Windows GPU build), Metal toolchain (macOS build), CMake, C++23 compiler
- Models: MuScriptor small (~210 MB), MuScriptor medium (~620 MB), MuScriptor large (~2.7 GB), GGUF
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Quick answers
Is neuralnote open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does neuralnote need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |